CD proposition-audit-anthony-searle
Post-hoc verification and trust audit of AI-generated factual and interpretive claims. Classifies claims by type and salience, routes them to domain-appropriate sources, scores trustworthiness on a tiered scale with an Interpolated verdict for plausible-but-unsupported detail, and assesses rhetorical fairness on interpretive claims. Designed for clinical-negligence and healthcare-law practice in England and Wales, with general applicability beyond.
Post-hoc verification and trust audit of AI-generated factual and interpretive claims.
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Execution cost. Instruction body is 4412 tokens
- 100Steps. 64 steps
- 100Consistency. Name and required fields are in place
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 452: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 64 items
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.